Bayesian active learning for multi‐objective feasible region identification in microwave devices

Abstract

Abstract In microwave device and circuit design, many simulations are often needed to find a set of designs that satisfy one or multiple specifications chosen by the designer upfront: the feasible region. A novel Bayesian active learning framework is presented to accurately identify the feasible region with a low number of simulations. The technique leverages on a stochastic model to obtain an efficient and automated procedure. A suitable application example validates the proposed technique and shows its effectiveness to rapidly obtain many suitable designs.

Keywords

• Computer-aided circuit analysis and design
• Microwave circuits and devices
• Other topics in statistics
• Other topics in statistics
• Electronic engineering computing
• Machine learning (artificial intelligence)